© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 23461
    Prev
    Next
    INDEX
    Explanations

    references to new developments or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to new developments or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adelphia
    -0.75
    asia
    -0.74
    ffield
    -0.73
    ouse
    -0.72
    76561
    -0.71
    xual
    -0.70
    ertodd
    -0.70
    WARE
    -0.69
    Reloaded
    -0.69
    âĢ¦]
    -0.68
    POSITIVE LOGITS
    foundland
    1.10
    bie
    1.02
     arrivals
    1.01
    bies
    0.87
     hires
    0.85
     revenue
    0.84
     batch
    0.80
     generation
    0.79
     interim
    0.77
     occupant
    0.75
    Activations Density 0.086%

    No Known Activations